EN TR

Check It — User Guide

Listen to your machine with your phone and catch when it drifts from “its normal”.
This page is both a user guide and a small vibration/sound-analysis handbook — you can learn it from scratch.

by Tetractaon-device core · optional AI17 machine types5 languages
⬇ Get the app
Contents 1 · What Check It is and how it works 2 · Get started in 5 minutes 3 · Reading the result: 🟢🟡🔴, score, HI, trend 4 · Vibration & sound analysis lesson (FFT · harmonics · bearings · ISO) 5 · Fusion: sound + vibration 6 · Pro: CSV/WAV file analysis 7 · Tools & fun 8 · Tips for a good measurement 9 · Honesty & limits (important) 10 · FAQ

1 · What Check It is and how it works

Check It is not a fault-diagnosis device. It is a change-tracking and triage tool. In one sentence:

It learns the machine’s “own normal” while the machine is HEALTHY → then measures how far later listenings DRIFT from that normal. It does not say “this exact fault exists”; it says “this machine isn’t like it was — it has changed.”

To do that it uses two of your phone’s sensors:

On each listening it extracts a sound/vibration fingerprint and compares it to the learned “normal”. If the difference is large, it warns you. The core listening and analysis happen on your phone; the optional Oney AI advisor (PRO) is the one feature that uses the internet, and only with your consent.

2 · Get started in 5 minutes

① Add a machine

Give it a name (e.g. “AC”, “Pump 3”), pick its type (motor/pump/fan/fridge/car…). The app auto-selects the right sensor for that type and honestly tells you how much it can catch on that machine. If you know the speed (RPM), enter it — for the fault-type hint.

② ● Save Healthy

While the machine runs normally, rest the phone firmly on its housing for ~20 s. The app learns its own normal. Important: don’t record on a stopped/faulty machine — “normal” would be learned wrong.

③ ▶ Listen

Later, rest the phone again → it shows 🟢🟡🔴 + a score + a fault-type hint + a trend. If you listen regularly (e.g. weekly), the trend becomes meaningful.

④ History & trend

Every listening is saved. Tap the machine → past records + trend graph: see whether it is degrading over time.

🎙️ On first launch it asks for microphone permission — tap “Allow”. For vibration machines, to wake the accelerometer the phone vibrates itself for ~2 s (you no longer need to shake it by hand) — once it shows “✓ ENGAGED”, learning/listening begins. (If it doesn’t engage, gently shake the phone.)

3 · Reading the result

IndicatorMeaning
🟢 HEALTHYLow drift from normal — the machine is close to how it was learned.
🟡 WATCHNoticeable drift — track it, re-measure, check conditions.
🔴 CAUTIONLarge drift — something changed. Have an expert verify.
Score (0–100)Closer to 100 = closer to normal. Not an absolute “health grade”; it’s a fit to its own normal.
HIHealth Index — the raw distance from normal (compared against a threshold τ).
🔎 hintA likely fault-type guess from the spectrum shape (not certain — see below).

4 · Vibration & sound analysis lesson

This part helps you understand the graphs and “hints” in the app. You can follow it even with no prior knowledge.

4.1 · Wave (time) → Spectrum (frequency)

A vibration/sound signal rises and falls over time (a wave). If we split the same signal into “which frequencies it is made of” using the FFT (Fast Fourier Transform), we get its spectrum. Fault signatures hide in specific peaks of the spectrum.

Time (wave) → FFT → Frequency (spectrum)

In the app you see both graphs live: wave + spectrum (bars).

4.2 · Rotation frequency (1×) and its harmonics

A rotating machine’s base frequency is 1× = RPM ÷ 60 (Hz). Example: 1797 RPM → 1× ≈ 29.95 Hz. Its multiples 2×, 3×… are harmonics. Which harmonic dominates suggests a likely fault type:

base
What you see in the spectrumLikely type (hint)
1× dominant, few harmonicsImbalance / unbalance
2× high (more than half of 1×)Misalignment (coupling)
Many harmonics (1×+2×+3×+…)Mechanical looseness
Broadband high frequencyCavitation / wear / rubbing
The 🔎 hint in the app uses exactly these rules. It’s a hint, not a diagnosis — since we can’t measure phase, e.g. misalignment ↔ a bent shaft can’t be told apart for certain.

4.3 · Bearing frequencies (BPFO / BPFI / BSF / FTF)

Bearing faults produce their own characteristic frequencies. These are computed from the bearing geometry and speed by physics (not learned from example data):

Abbr.What
BPFOBall Pass Frequency, Outer race
BPFIBall Pass Frequency, Inner race
BSFBall/roller Spin Frequency
FTFFundamental Train (cage) Frequency

In the Pro section, if you enter the bearing geometry (ball count N, ball diameter d, pitch diameter D), it computes these frequencies exactly and checks whether there is a prominent peak at that point in the spectrum. Important limit: early bearing faults are high-frequency; a phone accelerometer is weak there → for bearings the phone is limited (let’s be honest).

4.4 · ISO 10816 / 20816 — vibration severity

For vibration velocity (mm/s RMS, 10–1000 Hz) there are international severity zones:

ZoneMeaning
A / BGood / acceptable (newly commissioned, or fine for long-term running)
CBorderline — not satisfactory for long-term, plan action
DCan cause damage — take action

The Pro section computes the ISO zone when the unit is mm/s and you selected the machine group + mount type. If the unit is g / m/s² (raw phone acceleration) ISO is not given directly (honest: velocity integration is a separate step) — instead a band-RMS is shown for information.

5 · Fusion: sound + vibration

On phones that have an accelerometer, for vibration machines Check It combines microphone + accelerometer (fusion). Why? Because the accelerometer is immune to acoustic noise: even if the surroundings are noisy, the vibration channel stays clean. In our lab measurements, for low-frequency faults (imbalance/misalignment) fusion was noticeably more robust under noise than mic-only.

On screen you see both sensors live: 🎙️ sound wave + 📳 vibration wave + the accelerometer’s real Hz rate (proof of streaming). If it says “Learned normal: fusion”, fusion is active.

6 · Pro: CSV/WAV file analysis

The Pro section loads an external vibration CSV or sound WAV and analyses it in detail (ideal if you captured data from a dedicated vibration device).

  1. Pick a file (CSV = vibration time-wave; WAV = sound).
  2. Form: type (vibration/sound), RPM, sample rate (fs), unit (mm/s / g / m/s²), ISO group/mount, bearing geometry (N, d, D).
  3. Analyse → spectrum graph + report: dominant frequency, 1×/2×/3× harmonic diagnosis, bearing frequencies, ISO zone, cavitation, and an analysis-reliability score.
The analysis reliability (0–100) comes from the system’s real numbers: signal clarity (peak/noise ratio) + frequency resolution + band fit. Honest label: this is “data/signal quality”, not “fault certainty”. Try it with the embedded ★ Try sample (real CWRU bearing data) in one tap — for an outer-race fault you’ll see a prominent peak at BPFO ≈ 107 Hz.

7 · Tools & fun

🩺 Stethoscope

Listen live with the mic amplified (use headphones). Like a digital stethoscope — catch sounds you can’t hear.

🔊 Define Sounds

Record + label your own sounds → the app recognises them live. Plus 521 built-in sounds (dog/bird/car…) recognised on-device (YAMNet).

🔀 Which is Faulty?

Measure several units → it finds the one most deviating from the average. Quick triage for a fleet/workshop.

⏮ Before / After

Compare two measurements (before↔after maintenance, last month↔this month): % change + difference spectrum.

As you do regular checks you earn 🌱→🥉→🥈→🏆 badges — to build the habit.

8 · Tips for a good measurement

9 · Honesty & limits (important)

Check It is NOT a diagnosis/guarantee device. Its results are probabilistic hints. It is not a certified safety/measuring instrument and does not replace professional inspection. Do not make safety-critical decisions on this app alone; for anything important, have a qualified professional verify.

10 · FAQ

Do I need internet?

Not for the core change-tracking — it runs fully on your device. The optional Oney AI advisor (PRO) does need internet (it sends your question to a cloud AI provider, only with your consent).

What if my phone has no accelerometer/temperature sensor?

With no accelerometer it works mic-only (it says so honestly). Most phones have no ambient-temperature sensor; if present it uses it, otherwise it says “none” (we never show battery heat as machine heat).

How do I back up my data?

On the main screen: Backup (a single JSON file) / Restore. Your data is yours; export/delete anytime.

Is “score 100” always good?

The score is relative to the normal you learned. If you taught the normal wrong (while faulty), it misleads — teach it while healthy.